Krzysztof Krawiec


Home

Research:

edit SideBar

We propose a learning algorithm that reuses knowledge acquired in past learning sessions to improve its performance on a new learning task. The method concerns visual learning and uses genetic programming to represent hypotheses, each of them being a procedure that processes visual primitives derived from the training images. The process of recognition is generative, i.e., a procedure is supposed to restore the shape of the processed object by drawing its reproduction on a separate canvas. This basic method is extended with a knowledge reuse mechanism that allows learners to import genetic material from hypotheses that evolved for the other decision classes (object classes). We compare both methods on a task of handwritten character recognition, and conclude that knowledge reuse leads to significant improvement of classification accuracy and reduces the risk of overfitting.

@INPROCEEDINGS { Jaskowski07PlanLearn,
    AUTHOR = { Wojciech Jaƛkowski and Krzysztof Krawiec and Bartosz Wieloch },
    TITLE = { Evolutionary Learning with Cross-Class Knowledge Reuse for Handwritten Character Recognition },
    BOOKTITLE = { Proceedings of Planning to Learn Workshop, PlanLearn'07 },
    YEAR = { 2007 },
    EDITOR = { Pavel Brazdil and Abraham Bernstain },
    PAGES = { 21 -- 30 },
    ABSTRACT = { We propose a learning algorithm that reuses knowledge acquired in past learning sessions to improve its performance on a new learning task. The method concerns visual learning and uses genetic programming to represent hypotheses, each of them being a procedure that processes visual primitives derived from the training images. The process of recognition is generative, i.e., a procedure is supposed to restore the shape of the processed object by drawing its reproduction on a separate canvas. This basic method is extended with a knowledge reuse mechanism that allows learners to import genetic material from hypotheses that evolved for the other decision classes (object classes). We compare both methods on a task of handwritten character recognition, and conclude that knowledge reuse leads to significant improvement of classification accuracy and reduces the risk of overfitting. },
    URL = { http://www.cs.put.poznan.pl/kkrawiec/pubs/2007ECMLPlanLearn.pdf },
}


Powered by PmWiki